wav2vec2-large-xls-r-300m-assamese

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9825
• Wer: 0.6470

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.2484	9.8765	400	1.4669	0.9065
0.515	19.7531	800	0.9403	0.6835
0.1359	29.6296	1200	0.9825	0.6470

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1